Picsart API Platform
← All models

Seed Audio

Seed Audio · Audio · Text → Speech

Synthesize natural English or Chinese speech — pick a named voice or clone one from a reference audio.

Model ID: seed-audio-1.0Workflow: bytedance/text-to-speech
Voice CloningReference Audio
Try on Playground ↗

Install the SDK

The SDK targets Node 20+ and ships with TypeScript types.

npm
npm install @picsart/ai-sdk

Authenticate

Create a client once with your API key — it's sent as a bearer token on every request.

TypeScript
import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY, // sent as: Authorization: Bearer <key>
  apiUrl: 'https://api.picsart.com',
});

Run the model

Call the model with its parameters. This example uses the required ones.

TypeScript
import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

const result = await ai.generate('seed-audio-1.0', {
  prompt: "A serene mountain lake at golden hour, ultra detailed"
});

console.log(result.url); // audio URL

Parameters

10 parameters. Required ones must be supplied; the rest fall back to their defaults. The API takes these same names over HTTP.

ParameterTypeRequiredDefaultDetails
prompt
Prompt
textyesmax 3000 chars
voiceId
Voice
catalognoen_male_tim_uranus_bigttsoptions from bytedance/v1/catalog/voices (seed-audio-1.0)
audioUrls
Reference Audios
file (audio[])no
imageUrls
Reference Image
file (image[])no
format
Format
enumnowavwav, mp3, pcm, ogg_opus
sampleRate
Sample Rate
enumno441008000, 16000, 24000, 32000, 44100, 48000
speechRate
Speech Rate
rangeno0-50–100
loudnessRate
Loudness
rangeno0-50–100
pitchRate
Pitch
rangeno0-12–12
aigcWatermark
Watermark
booleannofalse

Output

generate() resolves once the job completes. An audio URL.

Result
{
  "url": "https://cdn.picsart.com/…/result",
  "results": [
    {
      "url": "https://cdn.picsart.com/…/result"
    }
  ],
  "model": "seed-audio-1.0"
}